Composum AI 0.7.1

Release summary

There are several improvements for the content creation dialog for both the Composum and AEM variant.

• In the content creation dialog the ist of sources for text generation is now extended with texts referenced in the component or containing / close components, then these can be chosen in the source selection menu as well.
• It is possible to use external URLs as text source for the text generation.
• Image recognition support: if gpt4-vision-preview is configured as model for use with images, then any image references found in the component or siblings then those are added as well to the source list, e.g to automatically generate image descriptions for blind users.

Downloads

Composum Pages

• Try it live on cloud.composum.com
• As Sling package: https://central.sonatype.com/artifact/com.composum.ai/composum-ai-integration-composum-package/0.7.0
• Prepackaged in the Composum Starter and docker image composum/featurelauncher-composum , both created in the Composum Launcher project.

AEM

• Download and install the package , configure an OpenAI API Key at "GPT Chat Completion Service" .
• Or add the Composum AI for AEM all package on Maven Central to your deployment.

Dependencies

This is an extension of Pages and needs at least
version 1.5.1.

What's Changed

• add external URL as source for content creation dialog by @stoerr in #43
• Image recognition, external URLs, content references by @stoerr in #44
• Some dependency updates by @dependabot in #45 , #46 , #47

Full Changelog: composum-ai-integration-0.7.0...composum-ai-integration-0.7.1